[英]Tokenize tweet based on Regex
我有以下示例文本/推文:
RT @trader $AAPL 2012 is o´o´o´o´o´pen to ‘Talk’ about patents with GOOG definitely not the treatment #samsung got:-) heh url_that_cannot_be_posted_on_SO
我想在Li, T, van Dalen, J, & van Rees, PJ (Pieter Jan) 中遵循表 1 的程序 。 (2017)。 不僅僅是噪音? 考察金融市場股票微博的信息內容。 信息技術雜志。 doi:10.1057/s41265-016-0034-2以清理推文。
他們以這樣的方式清理推文,最終結果是:
{RT|123456} {USER|56789} {TICKER|AAPL} {NUMBER|2012} notooopen nottalk patent {COMPANY|GOOG} notdefinetli treatment {HASH|samsung} {EMOTICON|POS} haha {URL}
我使用以下腳本根據正則表達式標記推文:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re
emoticon_string = r"""
(?:
[<>]?
[:;=8] # eyes
[\-o\*\']? # optional nose
[\)\]\(\[dDpP/\:\}\{@\|\\] # mouth
|
[\)\]\(\[dDpP/\:\}\{@\|\\] # mouth
[\-o\*\']? # optional nose
[:;=8] # eyes
[<>]?
)"""
regex_strings = (
# URL:
r"""http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"""
,
# Twitter username:
r"""(?:@[\w_]+)"""
,
# Hashtags:
r"""(?:\#+[\w_]+[\w\'_\-]*[\w_]+)"""
,
# Cashtags:
r"""(?:\$+[\w_]+[\w\'_\-]*[\w_]+)"""
,
# Remaining word types:
r"""
(?:[+\-]?\d+[,/.:-]\d+[+\-]?) # Numbers, including fractions, decimals.
|
(?:[\w_]+) # Words without apostrophes or dashes.
|
(?:\.(?:\s*\.){1,}) # Ellipsis dots.
|
(?:\S) # Everything else that isn't whitespace.
"""
)
word_re = re.compile(r"""(%s)""" % "|".join(regex_strings), re.VERBOSE | re.I | re.UNICODE)
emoticon_re = re.compile(regex_strings[1], re.VERBOSE | re.I | re.UNICODE)
######################################################################
class Tokenizer:
def __init__(self, preserve_case=False):
self.preserve_case = preserve_case
def tokenize(self, s):
try:
s = str(s)
except UnicodeDecodeError:
s = str(s).encode('string_escape')
s = unicode(s)
# Tokenize:
words = word_re.findall(s)
if not self.preserve_case:
words = map((lambda x: x if emoticon_re.search(x) else x.lower()), words)
return words
if __name__ == '__main__':
tok = Tokenizer(preserve_case=False)
test = ' RT @trader $AAPL 2012 is oooopen to ‘Talk’ about patents with GOOG definitely not the treatment #samsung got:-) heh url_that_cannot_be_posted_on_SO'
tokenized = tok.tokenize(test)
print("\n".join(tokenized))
這會產生以下輸出:
rt
@trader
$aapl
2012
is
oooopen
to
‘
talk
’
about
patents
with
goog
definitely
not
the
treatment
#samsung
got
:-)
heh
url_that_cannot_be_posted_on_SO
如何調整此腳本以獲得:
rt
{USER|trader}
{CASHTAG|aapl}
{NUMBER|2012}
is
oooopen
to
‘
talk
’
about
patents
with
goog
definitely
not
the
treatment
{HASHTAG|samsung}
got
{EMOTICON|:-)}
heh
{URL|url_that_cannot_be_posted_on_SO}
在此先感謝您幫助我度過了大半時間!
您確實需要使用命名捕獲組( 由 thebjorn 提到),並使用groupdict()
在每次匹配時獲取名稱-值對。 不過,它需要一些后期處理:
None
所有對self.preserve_case
為 false 該值可以立即變為小寫WORD
、 ELLIPSIS
或ELSE
則將值按原樣添加到words
中HASHTAG
、 CASHTAG
、 USER
或URL
,則添加的值首先在開頭去掉$
、 #
和@
字符,然后作為{<GROUP_NAME>|<VALUE>}
項添加到words
中{<GROUP_NAME>|<VALUE>}
項添加到words
中。 請注意, \\w
默認匹配下划線,因此[\\w_]
= \\w
。 我稍微優化了模式。
這是一個固定的代碼片段:
import re
emoticon_string = r"""
(?P<EMOTICON>
[<>]?
[:;=8] # eyes
[-o*']? # optional nose
[][()dDpP/:{}@|\\] # mouth
|
[][()dDpP/:}{@|\\] # mouth
[-o*']? # optional nose
[:;=8] # eyes
[<>]?
)"""
regex_strings = (
# URL:
r"""(?P<URL>https?://(?:[-a-zA-Z0-9_$@.&+!*(),]|%[0-9a-fA-F][0-9a-fA-F])+)"""
,
# Twitter username:
r"""(?P<USER>@\w+)"""
,
# Hashtags:
r"""(?P<HASHTAG>\#+\w+[\w'-]*\w+)"""
,
# Cashtags:
r"""(?P<CASHTAG>\$+\w+[\w'-]*\w+)"""
,
# Remaining word types:
r"""
(?P<NUMBER>[+-]?\d+(?:[,/.:-]\d+[+-]?)?) # Numbers, including fractions, decimals.
|
(?P<WORD>\w+) # Words without apostrophes or dashes.
|
(?P<ELLIPSIS>\.(?:\s*\.)+) # Ellipsis dots.
|
(?P<ELSE>\S) # Everything else that isn't whitespace.
"""
)
word_re = re.compile(r"""({}|{})""".format(emoticon_string, "|".join(regex_strings)), re.VERBOSE | re.I | re.UNICODE)
#print(word_re.pattern)
emoticon_re = re.compile(regex_strings[1], re.VERBOSE | re.I | re.UNICODE)
######################################################################
class Tokenizer:
def __init__(self, preserve_case=False):
self.preserve_case = preserve_case
def tokenize(self, s):
try:
s = str(s)
except UnicodeDecodeError:
s = str(s).encode('string_escape')
s = unicode(s)
# Tokenize:
words = []
for x in word_re.finditer(s):
for key, val in x.groupdict().items():
if val:
if not self.preserve_case:
val = val.lower()
if key in ['WORD','ELLIPSIS','ELSE']:
words.append(val)
elif key in ['HASHTAG','CASHTAG','USER','URL']: # Add more here if needed
words.append("{{{}|{}}}".format(key, re.sub(r'^[#@$]+', '', val)))
else:
words.append("{{{}|{}}}".format(key, val))
return words
if __name__ == '__main__':
tok = Tokenizer(preserve_case=False)
test = ' RT @trader $AAPL 2012 is oooopen to ‘Talk’ about patents with GOOG definitely not the treatment #samsung got:-) heh http://some.site.here.com'
tokenized = tok.tokenize(test)
print("\n".join(tokenized))
使用test = ' RT @trader $AAPL 2012 is oooopen to 'Talk' about patents with GOOG definitely not the treatment #samsung got:-) heh http://some.site.here.com'
,它輸出
rt
{USER|trader}
{CASHTAG|aapl}
{NUMBER|2012}
is
oooopen
to
‘
talk
’
about
patents
with
goog
definitely
not
the
treatment
{HASHTAG|samsung}
got
{EMOTICON|:-)}
heh
{URL|http://some.site.here.com}
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.